{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FUN5GJNVZFYEGYV5ZH67OPL4VT","short_pith_number":"pith:FUN5GJNV","schema_version":"1.0","canonical_sha256":"2d1bd325b5c9704362bdc9fdf73d7cacf9678429e7b17bd463331dd9aa033914","source":{"kind":"arxiv","id":"2606.04335","version":1},"attestation_state":"computed","paper":{"title":"Policy Gradient for Continuous-Time Robust Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Atsushi Nitanda, David M. Bossens, Tanya Veeravalli","submitted_at":"2026-06-03T01:25:20Z","abstract_excerpt":"The framework of robust Markov decision processes (RMDPs) allows the design of reinforcement learning agents that satisfy performance guarantees under worst-case transition dynamics. Traditional RMDPs consider discrete-time dynamics and recently, sample-efficient policy gradient algorithms have been considered in this context. This paper investigates policy gradient algorithms within a continuous-time RMDP framework. Policy gradients and adversarial gradients are derived using pathwise and adjoint-based formulas for stochastic and ordinary differential equations. We propose double-loop optimis"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.04335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T01:25:20Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"ec19bc947e75fb05fd94817e8ca4cd364619d8a2e0962deba2e93b39aa511a07","abstract_canon_sha256":"cc0ec36d19d8fbdc6db0ab7e94947236089b2f623b0856d61a549677687bb688"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:04.044432Z","signature_b64":"86UiLg9mTIVwNi9NLyEjf6KU+API1w3TS4u+eCgExohdE66QPKcJxrHVxI+RL5mknFo+17GLzard4hGNmmLDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d1bd325b5c9704362bdc9fdf73d7cacf9678429e7b17bd463331dd9aa033914","last_reissued_at":"2026-06-04T01:09:04.043994Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:04.043994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Gradient for Continuous-Time Robust Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Atsushi Nitanda, David M. Bossens, Tanya Veeravalli","submitted_at":"2026-06-03T01:25:20Z","abstract_excerpt":"The framework of robust Markov decision processes (RMDPs) allows the design of reinforcement learning agents that satisfy performance guarantees under worst-case transition dynamics. Traditional RMDPs consider discrete-time dynamics and recently, sample-efficient policy gradient algorithms have been considered in this context. This paper investigates policy gradient algorithms within a continuous-time RMDP framework. Policy gradients and adversarial gradients are derived using pathwise and adjoint-based formulas for stochastic and ordinary differential equations. We propose double-loop optimis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04335","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.04335/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.04335","created_at":"2026-06-04T01:09:04.044057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04335v1","created_at":"2026-06-04T01:09:04.044057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04335","created_at":"2026-06-04T01:09:04.044057+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUN5GJNVZFYE","created_at":"2026-06-04T01:09:04.044057+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUN5GJNVZFYEGYV5","created_at":"2026-06-04T01:09:04.044057+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUN5GJNV","created_at":"2026-06-04T01:09:04.044057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FUN5GJNVZFYEGYV5ZH67OPL4VT","json":"https://pith.science/pith/FUN5GJNVZFYEGYV5ZH67OPL4VT.json","graph_json":"https://pith.science/api/pith-number/FUN5GJNVZFYEGYV5ZH67OPL4VT/graph.json","events_json":"https://pith.science/api/pith-number/FUN5GJNVZFYEGYV5ZH67OPL4VT/events.json","paper":"https://pith.science/paper/FUN5GJNV"},"agent_actions":{"view_html":"https://pith.science/pith/FUN5GJNVZFYEGYV5ZH67OPL4VT","download_json":"https://pith.science/pith/FUN5GJNVZFYEGYV5ZH67OPL4VT.json","view_paper":"https://pith.science/paper/FUN5GJNV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04335&json=true","fetch_graph":"https://pith.science/api/pith-number/FUN5GJNVZFYEGYV5ZH67OPL4VT/graph.json","fetch_events":"https://pith.science/api/pith-number/FUN5GJNVZFYEGYV5ZH67OPL4VT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUN5GJNVZFYEGYV5ZH67OPL4VT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUN5GJNVZFYEGYV5ZH67OPL4VT/action/storage_attestation","attest_author":"https://pith.science/pith/FUN5GJNVZFYEGYV5ZH67OPL4VT/action/author_attestation","sign_citation":"https://pith.science/pith/FUN5GJNVZFYEGYV5ZH67OPL4VT/action/citation_signature","submit_replication":"https://pith.science/pith/FUN5GJNVZFYEGYV5ZH67OPL4VT/action/replication_record"}},"created_at":"2026-06-04T01:09:04.044057+00:00","updated_at":"2026-06-04T01:09:04.044057+00:00"}